quantum-neural-network

A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum computers.

Reimplementing the hybrid quantum-classical models from the paper "Quantum machine learning for image classification" by Arsenii Senokosov et al (https://arxiv.org/pdf/2304.09224.pdf)

Master quantum computing from zero to quantum machine learning. 20 interactive Jupyter notebooks, 10 real-world projects, curated resources & research papers. Qiskit, Cirq, PennyLane.

Python toolkit for noise-resilient classification. Focuses on interactive tensor-network simulation, automated testing, and spin-network encodings.

Quantum-inspired Leaky Integrate-and-Fire (QLIF) neurons for PyTorch, adaptive thresholds, dynamic spike probabilities, synaptic plasticity, neuromodulation, and optional qubit-based spike decisions.

Preregistered study: a noise model built from a self-collected month of hourly ibm_fez calibration snapshots predicts real hardware behavior of a hybrid quantum neural network to 0.5 pt. Part of the IRMB program.

Controlled interpolation between classical and quantum learning. Binarized Quantum Neural Network benchmark harness for systematic sweeping a quantumness parameter to map learning phase transitions.

Demo of quantum cryptanalysis combining Shor's Algorithm for RSA factorization with Quantum Neural Networks for cryptographic security assessment, running on real IBM quantum computers.

Hybrid Quantum–Classical Neural Network (QCNN) for automated brain tumour detection using MRI images. Combines EfficientNet-B0 feature extraction with a 4-qubit PennyLane quantum layer and includes a Gradio-based prediction interface.

A quantum machine learning toolkit built on Cqlib, featuring quantum data encoders, parameterized quantum circuits, quantum and hybrid quantum-classical neural networks, quantum kernel methods, and end-to-end training components.

Quantum-enhanced SAM for skin lesion segmentation on ISIC 2018. Hybrid SAM + Quantum Channel Attention achieves 91.23% IoU.

Hybrid Quantum-Classical Neural Network for MNIST digit classification using Qiskit and PyTorch. Features optimized training configurations, gradient clipping, and comprehensive visualization tools.

Hybrid quantum-classical Transformer LLM: attention is the fidelity between quantum states, not a dot product. Trained on Spanish books, with classical baseline, ablations and IBM Quantum adapters. // Transformer híbrido cuántico-clásico: la atención es fidelidad entre estados cuánticos.

TQ-HQNet: A Trainability-Aware and Qubit-Efficient Hybrid Quantum Neural Network for Cross-Domain Learning on Heterogeneous Data

Quantum Neural Network binary classifier using parameterized quantum circuits built from scratch with Qiskit

Creating a QNN to predict trends in the stock market

Quantum Machine Learning portfolio for ML4SCI QMLHEP, featuring QGANs, QGNNs, QRL, EQNNs, and Vision Transformers built with TensorFlow Quantum and Cirq.